Skip to main content

Research Repository

Advanced Search

Evaluation of frameworks that combine evolution and learning to design robots in complex morphological spaces

Li, Wei; Buchanan, Edgar; Goff, Léni K. Le; Hart, Emma; Hale, Matthew F.; Wei, Bingsheng; Carlo, Matteo De; Angus, Mike; Woolley, Robert; Gan, Zhongxue; Winfield, Alan F.; Timmis, Jon; Eiben, Agoston E.; Tyrrell, Andy M.

Evaluation of frameworks that combine evolution and learning to design robots in complex morphological spaces Thumbnail


Authors

Wei Li

Edgar Buchanan

Léni K. Le Goff

Emma Hart

Matthew F. Hale

Bingsheng Wei

Matteo De Carlo

Mike Angus

Robert Woolley

Zhongxue Gan

Jon Timmis

Agoston E. Eiben

Andy M. Tyrrell



Abstract

Jointly optimising both the body and brain of a robot is known to be a challenging task, especially when attempting to evolve designs in simulation that will subsequently be built in the real world. To address this, it is increasingly common to combine evolution with a learning algorithm that can either improve the inherited controllers of new offspring to fine tune them to the new body design or learn them from scratch. In this paper an approach is proposed in which a robot is specified indirectly by two compositional pattern producing networks (CPPN) encoded in a single genome, one which encodes the brain and the other the body. The body part of the genome is evolved using an evolutionary algorithm (EA), with an individual learning algorithm (also an EA) applied to the inherited controller to improve it. The goal of this paper is to determine how to utilise the results of learning process most effectively to improve task performance of the robot. Specifically, three variants are investigated: (1) evolution of the body+controller only; (2) a learning algorithm is applied to the inherited controller with the learned fitness assigned to the genome; (3) learning is applied and the genome is updated with the learned controller, as well as being assigned the learned fitness. Experiments are performed in three different scenarios chosen to favour different bodies and locomotion patterns. It is shown that better performance can be obtained using learning but only if the learned controller is inherited by the offspring.

Citation

Li, W., Buchanan, E., Goff, L. K. L., Hart, E., Hale, M. F., Wei, B., …Tyrrell, A. M. (in press). Evaluation of frameworks that combine evolution and learning to design robots in complex morphological spaces. IEEE Transactions on Evolutionary Computation, https://doi.org/10.1109/tevc.2023.3316363

Journal Article Type Article
Acceptance Date Sep 6, 2023
Online Publication Date Dec 8, 2023
Deposit Date Dec 15, 2023
Publicly Available Date Jan 3, 2024
Journal IEEE Transactions on Evolutionary Computation
Print ISSN 1089-778X
Electronic ISSN 1089-778X
Publisher Institute of Electrical and Electronics Engineers
Peer Reviewed Peer Reviewed
DOI https://doi.org/10.1109/tevc.2023.3316363
Keywords Computational Theory and Mathematics; Theoretical Computer Science; Software
Public URL https://uwe-repository.worktribe.com/output/11518131

Files

Evaluation Of Frameworks That Combine Evolution And Learning To Design Robots In Complex Morphological Spaces (45.3 Mb)
PDF

Licence
http://www.rioxx.net/licenses/all-rights-reserved

Copyright Statement
© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works





You might also like



Downloadable Citations